Have a look at each of the variables
skim(mercury_data)
| Name | mercury_data |
| Number of rows | 513 |
| Number of columns | 20 |
| _______________________ | |
| Column type frequency: | |
| character | 3 |
| factor | 5 |
| numeric | 12 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| URL | 0 | 1.00 | 40 | 1777 | 0 | 79 | 0 |
| Sex of Sample (if only one sample) | 498 | 0.03 | 4 | 6 | 0 | 2 | 0 |
| Main Findings/Comments | 408 | 0.20 | 12 | 476 | 0 | 76 | 0 |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| Authors | 0 | 1.00 | FALSE | 44 | Rüd: 36, K. : 33, N M: 30, Dou: 29 |
| Title | 0 | 1.00 | FALSE | 44 | A f: 36, Dis: 33, Mer: 30, A C: 29 |
| Location Description | 0 | 1.00 | FALSE | 152 | Ion: 30, Lak: 20, Riv: 18, Moj: 16 |
| Region | 0 | 1.00 | FALSE | 10 | Nor: 148, Asi: 90, Nor: 63, Sou: 48 |
| Type of Fish | 5 | 0.99 | FALSE | 192 | Atl: 30, Pik: 23, Sna: 20, Rai: 17 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| Published | 0 | 1.00 | 2004.53 | 13.63 | 1975.00 | 1997.00 | 2007.00 | 2017.00 | 2020.00 | ▃▁▅▃▇ |
| Data collected (first) | 47 | 0.91 | 1999.29 | 13.74 | 1972.00 | 1989.25 | 2000.50 | 2010.00 | 2017.00 | ▃▂▃▃▇ |
| Data collected (last) | 248 | 0.52 | 2007.18 | 10.35 | 1973.00 | 2000.00 | 2011.00 | 2012.00 | 2017.00 | ▁▁▂▁▇ |
| Latitude | 0 | 1.00 | 21.09 | 28.79 | -41.83 | 1.44 | 25.08 | 45.27 | 71.04 | ▃▆▇▇▇ |
| Longitude | 0 | 1.00 | 22.19 | 86.38 | -116.63 | -74.82 | 16.62 | 107.44 | 178.07 | ▇▁▇▃▅ |
| Number of Samples | 261 | 0.49 | 11.82 | 38.80 | 1.00 | 1.00 | 5.00 | 11.00 | 547.00 | ▇▁▁▁▁ |
| Length of Fish (cm) | 283 | 0.45 | 91.43 | 126.65 | 5.03 | 22.51 | 42.30 | 108.50 | 939.60 | ▇▁▁▁▁ |
| Weight of Fish (g) | 264 | 0.49 | 29650.35 | 85129.48 | 2.00 | 184.00 | 1020.00 | 3550.00 | 540000.00 | ▇▁▁▁▁ |
| Age (years) | 430 | 0.16 | 9.83 | 6.11 | 2.00 | 4.65 | 8.00 | 15.00 | 21.00 | ▇▃▃▂▅ |
| Conc Hg Fish [ug/g] | 3 | 0.99 | 0.46 | 0.72 | 0.00 | 0.07 | 0.24 | 0.57 | 10.10 | ▇▁▁▁▁ |
| Conc Hg Water [ug/mL] | 506 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.04 | ▇▁▁▁▁ |
| Conc Hg Sediment [ug/g] | 456 | 0.11 | 0.35 | 0.71 | 0.00 | 0.01 | 0.06 | 0.14 | 2.63 | ▇▁▁▁▁ |
(fish_summary <-
mercury_data %>%
mutate(`Number of Samples` = if_else(is.na(`Number of Samples`),1,`Number of Samples`)) %>%
group_by(`Type of Fish`) %>%
summarise(Samples = sum(`Number of Samples`),
mean_conc = round( mean(`Conc Hg Fish [ug/g]`),3),
sd_conc = round( sd(`Conc Hg Fish [ug/g]`),3),
.groups = "drop") %>%
{mutate(.,`Type of Fish` = factor(x = `Type of Fish`,
levels = `Type of Fish`[order(Samples,decreasing = T)],
ordered = T))} %>%
arrange(desc(Samples))) %>%
DT::datatable()
fish_summary %>%
ggplot(aes(x = `Type of Fish`,y = Samples))+
geom_bar(stat = "identity")+
theme(axis.text.x = element_text(angle = 90,hjust = 1,size = 4))
fish_summary %>%
filter(as.numeric(`Type of Fish`)<=15) %>%
{ggplot(.,aes(x = `Type of Fish`,y = Samples))+
geom_bar(stat = "identity")+
theme(axis.text.x = element_text(angle = 90,hjust = 1, size = 7))} %>% ggplotly(height = 500)
mercury_data %>%
{ggplot(.,aes(x = `Length of Fish (cm)`))+
geom_histogram()} %>%
ggplotly
Length < 1m
mercury_data %>%
filter(`Length of Fish (cm)`<100) %>%
{ggplot(.,aes(x = `Length of Fish (cm)`))+
geom_histogram()} %>%
ggplotly
mercury_data %>%
{ggplot(.,aes(x = `Weight of Fish (g)`))+
geom_histogram()} %>%
ggplotly
Weight < 10kg
mercury_data %>%
filter(`Weight of Fish (g)`< 10000) %>%
{ggplot(.,aes(x = `Weight of Fish (g)`))+
geom_histogram()} %>%
ggplotly
mercury_data %>%
{ggplot(.,aes(x = `Age (years)`))+
geom_histogram()} %>%
ggplotly
Age < 10 years
mercury_data %>%
filter(`Age (years)`<10) %>%
{ggplot(.,aes(x = `Age (years)`))+
geom_histogram()} %>%
ggplotly
mercury_data %>%
select(`Length of Fish (cm)`,
`Weight of Fish (g)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Length of Fish (cm)`,
y = `Weight of Fish (g)`,
color = `Type of Fish`))+
geom_point()+
coord_cartesian(xlim = c(0,300))+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Length of Fish (cm)`,
`Weight of Fish (g)`,
`Type of Fish`) %>%
na.omit %>%
filter(`Length of Fish (cm)`>100,
`Weight of Fish (g)`>10000) %>%
# filter(grepl("(tuna|shark)",
# as.character(`Type of Fish`),
# ignore.case = TRUE)) %>%
{ggplot(.,aes(x = `Length of Fish (cm)`,
y = `Weight of Fish (g)`,
color = `Type of Fish`))+
geom_point()+
coord_cartesian(xlim = c(0,300))+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Length of Fish (cm)`,
`Weight of Fish (g)`,
`Type of Fish`) %>%
na.omit %>%
filter(`Length of Fish (cm)`<=100,
`Weight of Fish (g)`<=10000) %>%
# filter(!grepl("(tuna|shark)",
# as.character(`Type of Fish`),
# ignore.case = TRUE)) %>%
{ggplot(.,aes(x = `Length of Fish (cm)`,
y = `Weight of Fish (g)`,
color = `Type of Fish`))+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Age (years)`,
`Weight of Fish (g)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Age (years)`,
y = `Weight of Fish (g)`,
color = `Type of Fish`))+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Age (years)`,
`Length of Fish (cm)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Age (years)`,
y = `Length of Fish (cm)`,
color = `Type of Fish`))+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`))+
geom_vline(xintercept = 0.5, color = "red")+
geom_histogram()} %>%
ggplotly
Everything below 4 ug/g
mercury_data %>%
filter(`Conc Hg Fish [ug/g]`<4) %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`))+
geom_vline(xintercept = 0.5, color = "red")+
geom_histogram()} %>%
ggplotly
mercury_data %>%
{ggplot(.,aes(x = `Conc Hg Sediment [ug/g]`))+
geom_histogram()} %>%
ggplotly
Everything below 1 ug/g
mercury_data %>%
filter(`Conc Hg Sediment [ug/g]`<1) %>%
{ggplot(.,aes(x = `Conc Hg Sediment [ug/g]`))+
geom_histogram()} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
`Length of Fish (cm)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`,
y = `Length of Fish (cm)`,
color = `Type of Fish`))+
geom_vline(xintercept = 0.5,color = "red")+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
`Weight of Fish (g)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`,
y = `Weight of Fish (g)`,
color = `Type of Fish`))+
geom_vline(xintercept = 0.5,color = "red")+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
`Age (years)`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`,
y = `Age (years)`,
color = `Type of Fish`))+
geom_vline(xintercept = 0.5,color = "red")+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
Published,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`,
y = Published,
color = `Type of Fish`))+
geom_vline(xintercept = 0.5,color = "red")+
geom_point()+
theme(legend.position = 'none')} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
`Conc Hg Sediment [ug/g]`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Conc Hg Fish [ug/g]`,
y = `Conc Hg Sediment [ug/g]`,
color = `Type of Fish`))+
geom_vline(xintercept = 0.5,color = "red")+
geom_point()+
theme(legend.position = 'none')+
coord_cartesian(expand = FALSE)} %>%
ggplotly
mercury_data %>%
select(`Conc Hg Fish [ug/g]`,
Region) %>%
na.omit %>%
{ggplot(.,aes(x = Region,
y = `Conc Hg Fish [ug/g]`))+
geom_hline(yintercept = 0.5,color = "red")+
geom_boxplot()+
theme(legend.position = 'none')+
coord_cartesian(expand = FALSE)}
mercury_data %>%
mutate(`Type of Fish` = factor(x = `Type of Fish`,levels = fish_summary$`Type of Fish`[order(fish_summary$mean_conc,decreasing = T)])) %>%
select(`Conc Hg Fish [ug/g]`,
`Type of Fish`) %>%
na.omit %>%
{ggplot(.,aes(x = `Type of Fish`,
y = `Conc Hg Fish [ug/g]`,
text = `Type of Fish`))+
geom_hline(yintercept = 0.5,color = "red")+
geom_boxplot()+
theme(axis.text.x = element_text(angle = 90, hjust = 1, size = 6),
legend.position = 'none')+
coord_cartesian(expand = FALSE)} %>%
ggplotly(tooltip = "text")
mercury_data %>%
mutate(`Type of Fish` = factor(x = `Type of Fish`,
levels = fish_summary$`Type of Fish`[order(fish_summary$mean_conc,
decreasing = T)])) %>%
select(`Conc Hg Fish [ug/g]`,
`Type of Fish`) %>%
na.omit %>%
filter(as.numeric(`Type of Fish`)<=20) %>%
{ggplot(.,aes(x = `Type of Fish`,
y = `Conc Hg Fish [ug/g]`,
text = `Type of Fish`))+
geom_hline(yintercept = 0.5,color = "red")+
geom_boxplot()+
theme(axis.text.x = element_text(angle = 90, hjust = 1),
legend.position = 'none')+
coord_cartesian(expand = FALSE)} %>%
ggplotly(tooltip = "text")